3D Hand Pose Estimation via Aligned Latent Space Injection and Kinematic Losses


In this paper, we propose a novel multi-stage deep learning methodology to accurately tackle the problem of hand pose estimation. More specifically, we initially propose a disentanglement stage to differentiate the significant pose-specific information from the irrelevant background noise and illumination variations of RGB images. Then, we introduce a variational alignment stage to accurately align the latent spaces of the pose-specific and the true hand pose information, effectively improving the discrimination ability of the proposed methodology. Finally, we propose two loss terms to impose physiological and geometrical kinematic constraints to the predicted hand poses, empowering the proposed methodology to avoid non-plausible poses. During all stages, a novel injection decoder is introduced, improving significantly the decoding accuracy of the latent space. Extensive experimentation on two well-known datasets (i.e., RHD and STB) validate the ability of the proposed methodology to achieve accurate hand pose estimation results, overcoming current state-of-the-art methods.

  • A. Stergioulas, T. Chatzis, D. Konstantinidis, K. Dimitropoulos, P. Daras, "3D Hand Pose Estimation via Aligned Latent Space Injection and Kinematic Losses", in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June, 2021.

  • Visual Computing Lab

    The focus of the Visual Computing Laboratory is to develop new algorithms and architectures for applications in the areas of 3D processing, image/video processing, computer vision, pattern recognition, bioinformatics and medical imaging.

    Download VCL Leaflet

    Contact Information

    Dr. Petros Daras, Research Director
    6th km Charilaou – Thermi Rd, 57001, Thessaloniki, Greece
    P.O.Box: 60361
    Tel.: +30 2310 464160 (ext. 156)
    Fax: +30 2310 464164
    Email: daras(at)iti(dot)gr